sveltekit
Mental-model reset for SvelteKit apps. Use when writing or reviewing routes, layouts, load functions, form actions, remote functions, hooks, auth, cookies, endpoints, redirects, errors, SSR, progressive enhancement, or app-level data flow. Triggers on SvelteKit, +page, +layout, +server, +page.server.ts, +layout.server.ts, hooks.server.ts, load, actions, fail(), redirect(), error(), cookies, locals, route groups, protected routes, sessions, form actions, enhance, remote functions, command(), query(), form(), getRequestEvent(), SSR, hydration, and serialization. Use svelte5 for component-level runes, snippets, accessibility, actions, transitions, and component API review.
93
92%
Does it follow best practices?
Impact
93%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities, provides extensive natural trigger terms, explicitly states both what and when, and carefully distinguishes itself from a related svelte5 skill. The description is comprehensive without being padded—every term serves a purpose for skill selection. The only minor note is that 'Mental-model reset' is slightly abstract as an opening phrase, but the rest of the description more than compensates.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists numerous specific concrete actions and concepts: routes, layouts, load functions, form actions, remote functions, hooks, auth, cookies, endpoints, redirects, errors, SSR, progressive enhancement, and app-level data flow. It goes well beyond naming a domain. | 3 / 3 |
Completeness | Clearly answers both 'what' (mental-model reset for SvelteKit apps covering routes, layouts, load functions, etc.) and 'when' (explicit 'Use when...' clause with comprehensive trigger scenarios, plus a 'Triggers on' list). Also includes boundary guidance distinguishing from the svelte5 skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually use, including file naming conventions (+page, +page.server.ts, hooks.server.ts), function names (fail(), redirect(), error(), load), and conceptual terms (SSR, hydration, protected routes, sessions). Also includes disambiguation guidance pointing users to svelte5 for component-level concerns. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (SvelteKit app-level concerns) and explicit boundary drawn against a related skill (svelte5 for component-level work). The specific file conventions and SvelteKit-specific API terms make accidental triggering for unrelated skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted mental-model skill that efficiently communicates SvelteKit's architectural philosophy through numbered principles, anti-patterns, and a decision lookup table. Its main strength is conciseness and progressive disclosure—it serves as an excellent routing layer to deeper reference files. The primary weakness is the absence of executable code examples in the main file; the skill describes correct behavior rather than demonstrating it, relying on reference files for concrete implementation details.
Suggestions
Add 1-2 minimal executable code examples for the most critical patterns (e.g., a correct server load function returning serializable data, or a form action with fail() validation) to boost actionability without sacrificing conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every sentence carries weight. The skill assumes Claude's competence with web development concepts, never explains what SvelteKit is at a basic level, and uses terse numbered principles with direct references. The 'Common Mistakes' section is a compact lookup table, not a tutorial. | 3 / 3 |
Actionability | The skill provides clear mental models and anti-patterns but lacks executable code examples. Guidance is specific and concrete (e.g., 'throw redirect()' not 'call redirect()'), but there are no copy-paste code snippets demonstrating correct patterns. The actionability relies heavily on the referenced files which are not provided. | 2 / 3 |
Workflow Clarity | This is a mental-model/decision-framework skill rather than a multi-step process skill. The numbered principles create a clear decision sequence (routes → data flow → forms → auth → remote functions → SSR), and the Quick Reference table provides an unambiguous 'smell → action → reference' lookup. For this type of skill, the workflow is the decision tree, and it's well-structured. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The main file is a concise overview with 17 numbered principles, each pointing to exactly one reference file. The Quick Reference table and Reference Index provide two navigation paths. All references are one level deep and clearly signaled with consistent markdown link formatting. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- joshuadavidthomas/agent-skills
- Commit
40067f1
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.